Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

YouTube

REMOTE · API.MCP.AI

Search, video, channel, playlist, comments, trending and related items from YouTube. Hosted by the p

Available components

0 this week 76 Trust /100

Last scanned (20 hours ago)

Scores higher than 65% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Entertainment and Games

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS enforcement could not be verified: the plaintext port answered with HTTP 406, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
  • HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability63
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 2938 tokens (~83/item across 35 items; 35 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 36 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (12)

  • TLS certificate
  • Authorization
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Checks we could not complete (1)

These are gaps on our side, not findings about this hosted endpoint. We only credit what we can confirm, so a category made up entirely of them scores 0.

  • HTTPS in Endpoint SecurityHTTPS enforcement could not be verified: the plaintext port answered with HTTP 406, which proves neither a plaintext path nor enforcement.

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 0.9.460 → 0.9.465 functional
  • 20 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 0.9.459 → 0.9.460 functional
  • 19 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 0.9.454 → 0.9.459 functional
  • 18 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 0.9.452 → 0.9.454 functional
  • 17 Nov 26 +44
    • Authorization: unverified → partial ▲ security
    • Injection markers: unverified → pass ▲ security
    • Stability: unverified → pass ▲ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool coverage: unverified → 100 ▲ functional
    • Server version: 0.9.449 → 0.9.452 functional
  • 16 Nov 26 −44
    • Stability: pass → unverified ▼ security
    • Tool safety: pass → unverified ▼ security
    • Authorization: partial → unverified ▼ security
    • Tool coverage: 100 → unverified ▼ functional
    • This server's schema is too large to store in full, so we cannot compare its tools day to day functional
  • 15 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 0.9.440 → 0.9.449 functional
  • 14 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 0.9.425 → 0.9.440 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://api.mcp.ai/p_youtube

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.ai CN=WE1,O=Google Trust Services,C=US 28 Sept 2026 27 Dec 2026 ECDSA 256 ECDSA-SHA256 1bf4d405299e078a0e62ff16cded599b
SANs: mcp.ai, *.mcp.ai
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of api.mcp.ai. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
mcp.ai. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.mcp.ai/p_youtube Verified 200
http (plaintext) http://api.mcp.ai/p_youtube Inconclusive 406
MCP tools · 35 exposed · ~2,810 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
authenticate ~99

MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.

NameTypeReqDescription
tokenstring––

No output schema declared.

No examples provided.

connect ~42

Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

marketplace ~532

The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

NameTypeReqDescription
actionstring––
argumentsstring––
cancel_commentstring––
cancel_reasonstring––
conversationstring––
immediateboolean––
limitnumber––
mcp_idstring––
messagestring––
prompt_bodystring––
prompt_categorystring––
prompt_descriptionstring––
prompt_slugstring––
prompt_targetsarray––
prompt_titlestring––
prompt_toolstring––
prompt_varsstring––
querystring––
report_contextstring––
request_detailsstring––
request_namestring––
tier_slugstring––
tool_idstring––

No output schema declared.

No examples provided.

report_bug ~50

Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.

NameTypeReqDescription
contextstring––
conversationstring––
messagestringyes–

No output schema declared.

No examples provided.

show_version ~17

Show the current MCP platform and adapter versions.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

toolkit_info ~37

Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

youtube_api ~88

Escape hatch: call any path on the YouTube backend. Pass path (e.g. /search), optional method (default GET), query map, and JSON body for POST. Prefer the named youtube_* tools when available; this is for routes not in the manifest.

NameTypeReqDescription
body–––
methodstring––
pathstringyes–
queryobject––

No output schema declared.

No examples provided.

youtube_channel_about ~53

Channel description, links, country, subscriber count, banner. Bulk support: accepts ids for batched execution.

NameTypeReqDescription
forUsernamestring––
idstring––
idsarray––

No output schema declared.

No examples provided.

youtube_channel_community ~56

Community posts tab for a channel. Bulk support: accepts ids for batched execution.

NameTypeReqDescription
forUsernamestring––
idstring––
idsarray––
tokenstring––

No output schema declared.

No examples provided.

youtube_channel_featured ~79

Featured channels listed on a channel. Note: YouTube deprecated the featured-channels tab; this route exists upstream but typically returns an empty/error envelope. Bulk support: accepts ids for batched execution.

NameTypeReqDescription
forUsernamestring––
idstring––
idsarray––
tokenstring––

No output schema declared.

No examples provided.

youtube_channel_home ~58

Channel home page payload (featured shelves + meta). Bulk support: accepts ids for batched execution.

NameTypeReqDescription
forUsernamestring––
idstring––
idsarray––
tokenstring––

No output schema declared.

No examples provided.

youtube_channel_playlists ~61

Channel playlists tab. Bulk support: accepts ids for batched execution.

NameTypeReqDescription
forUsernamestring––
idstring––
idsarray––
sort_bystring––
tokenstring––

No output schema declared.

No examples provided.

youtube_channel_search ~64

Search a channel's own videos and playlists. Bulk support: accepts ids for batched execution.

NameTypeReqDescription
forUsernamestring––
idstring––
idsarray––
querystringyes–
tokenstring––

No output schema declared.

No examples provided.

youtube_channel_shorts ~53

Channel shorts tab. Bulk support: accepts ids for batched execution.

NameTypeReqDescription
forUsernamestring––
idstring––
idsarray––
tokenstring––

No output schema declared.

No examples provided.

youtube_channel_shorts_post ~85

POST variant of channel shorts. Requires a `params` continuation token from a prior GET response. Skip in daily smoke (no synthetic params). Bulk support: accepts ids for batched execution.

NameTypeReqDescription
forUsernamestring––
idstring––
idsarray––
paramsstringyes–
tokenstring––

No output schema declared.

No examples provided.

youtube_channel_store ~49

Store / merch shelf for a channel. Bulk support: accepts ids for batched execution.

NameTypeReqDescription
forUsernamestring––
idstring––
idsarray––

No output schema declared.

No examples provided.

youtube_channel_videos ~61

Channel videos tab. Bulk support: accepts ids for batched execution.

NameTypeReqDescription
forUsernamestring––
idstring––
idsarray––
sort_bystring––
tokenstring––

No output schema declared.

No examples provided.

youtube_channel_videos_post ~101

POST variant of channel videos. Requires a `params` continuation token captured from a prior GET response — used to fetch deeper pages or filtered shelves that the GET surface can't address. Skip in daily smoke (no synthetic params). Bulk support: accepts ids for batched execution.

NameTypeReqDescription
forUsernamestring––
idstring––
idsarray––
paramsstringyes–
tokenstring––

No output schema declared.

No examples provided.

youtube_comment_delete ~97

Apaga DEFINITIVAMENTE um comentário (não tem desfazer). Só funciona em comentário do próprio canal ou em vídeo do canal conectado. Para esconder sem apagar, prefira youtube_comment_moderate com `rejected`. Custa 50 unidades da cota. Bulk support: accepts comment_ids for batched execution.

NameTypeReqDescription
accountstring––
comment_idstringyes–
comment_idsarray––

No output schema declared.

No examples provided.

youtube_comment_moderate ~100

Modera comentários no canal conectado: publica (`published`), segura para revisão (`heldForReview`) ou rejeita (`rejected`). `ban_author` só é aceito junto de `rejected`. Vale apenas para comentários em vídeos do próprio canal. Custa 50 unidades por comentário.

NameTypeReqDescription
accountstring––
ban_authorboolean––
comment_idsarrayyes–
statusstringyes–

No output schema declared.

No examples provided.

youtube_comment_post ~85

Publica um comentário NOVO de topo em um vídeo, como o canal conectado. Para responder alguém, use youtube_comment_reply. Custa 50 unidades da cota. Bulk support: accepts video_ids for batched execution.

NameTypeReqDescription
accountstring––
textstringyes–
video_idstringyes–
video_idsarray––

No output schema declared.

No examples provided.

youtube_comment_reply ~123

Responde comentários como o canal conectado. Aceita VÁRIAS respostas numa chamada (`replies`), e um item que falha não derruba os outros. `parent_id` tem que ser o id de um comentário de TOPO (campo `id` do thread devolvido por youtube_comment_threads), nunca o id de uma resposta. Cada resposta consome 50 unidades da cota da API do YouTube, então responda o que importa em vez de varrer o canal.

NameTypeReqDescription
accountstring––
repliesarrayyes–

No output schema declared.

No examples provided.

youtube_comment_threads ~182

Comentários de TOPO pela API oficial, com as respostas já existentes. É daqui que sai o `parent_id` usado em youtube_comment_reply (o id do thread), então prefira esta tool a youtube_comments quando a intenção for responder. Sem `video_id`, traz os comentários do canal conectado inteiro (bom para 'o que ainda não respondi'). Custa 1 unidade da cota. Bulk support: accepts video_ids, channel_ids for batched execution.

NameTypeReqDescription
accountstring––
channel_idstring––
channel_idsarray––
max_resultsnumber––
moderation_statusstring––
orderstring––
page_tokenstring––
search_termsstring––
video_idstring––
video_idsarray––

No output schema declared.

No examples provided.

youtube_comment_update ~107

Edita o texto de um comentário ou resposta PUBLICADO pelo canal conectado (corrigir um erro sem apagar e repostar, o que perderia as curtidas e o encadeamento). Só funciona em comentário de autoria do próprio canal. Custa 50 unidades da cota. Bulk support: accepts comment_ids for batched execution.

NameTypeReqDescription
accountstring––
comment_idstringyes–
comment_idsarray––
textstringyes–

No output schema declared.

No examples provided.

youtube_comments ~55

Top-level comments thread for a video. Bulk support: accepts ids for batched execution.

NameTypeReqDescription
idstringyes–
idsarray––
sort_bystring––
tokenstring––

No output schema declared.

No examples provided.

youtube_download ~55

Stream/download metadata for a video (formats, audio/video URLs, status). Bulk support: accepts ids for batched execution.

NameTypeReqDescription
cgeostring––
idstringyes–
idsarray––

No output schema declared.

No examples provided.

youtube_hashtag ~39

Posts under a hashtag (without leading #).

NameTypeReqDescription
tagstringyes–
tokenstring––
typestring––

No output schema declared.

No examples provided.

youtube_home_feed ~41

YouTube home feed (anonymous, geo/lang aware).

NameTypeReqDescription
geostring––
langstring––
tokenstring––

No output schema declared.

No examples provided.

youtube_hype ~42

YouTube Hype: viral / hyped videos feed.

NameTypeReqDescription
geostring––
langstring––
tokenstring––

No output schema declared.

No examples provided.

youtube_my_channels ~65

Lista os canais do YouTube conectados (os que podem responder e moderar comentários), com id, nome e estatísticas. Use antes de responder para confirmar de qual canal a resposta vai sair. Custa 1 unidade da cota.

NameTypeReqDescription
accountstring––

No output schema declared.

No examples provided.

youtube_playlist ~45

Playlist items by playlist id. Bulk support: accepts ids for batched execution.

NameTypeReqDescription
idstringyes–
idsarray––
tokenstring––

No output schema declared.

No examples provided.

youtube_resolve_url ~33

Resolve a YouTube URL or share link to its videoId / pageType.

NameTypeReqDescription
urlstringyes–

No output schema declared.

No examples provided.

youtube_search ~73

Search videos, channels, playlists.

NameTypeReqDescription
durationstring––
geostring––
langstring––
querystringyes–
sort_bystring––
tokenstring––
typestring––
upload_datestring––

No output schema declared.

No examples provided.

youtube_trending ~35

Trending videos by region.

NameTypeReqDescription
geostring––
langstring––
typestring––

No output schema declared.

No examples provided.

youtube_video_related ~48

Related videos for a given video id. Bulk support: accepts ids for batched execution.

NameTypeReqDescription
idstringyes–
idsarray––
tokenstring––

No output schema declared.

No examples provided.

Install

How do I install the YouTube MCP server?

YouTube is a hosted endpoint at https://api.mcp.ai/p_youtube, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · api.mcp.ai

# add to Claude Code
claude mcp add --transport http mcp-dir-youtube-mcp 'https://api.mcp.ai/p_youtube'
Common questions

What is the YouTube MCP server?

YouTube is an MCP server listed in the public MCP registry as io.github.mcp-dir/youtube-mcp. Search, video, channel, playlist, comments, trending and related items from YouTube. Hosted by the p. This page covers its hosted endpoint (https://api.mcp.ai/p_youtube).

Is the YouTube MCP server safe to use?

YouTube scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the YouTube MCP server expose?

YouTube exposes 35 tools: youtube_home_feed, youtube_trending, youtube_search, youtube_resolve_url, youtube_download, and 30 more. Their descriptions and schemas cost roughly 2,810 tokens of context every time the server is loaded.

Does the YouTube MCP server require authentication?

No. We connected to YouTube without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the YouTube MCP server still maintained?

YouTube is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the YouTube MCP server?

VerifyMCP ran 12 checks on YouTube, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about YouTube: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.